Capture once.
Recall when it matters.
Recall Racoon gives your AI systems persistent memory. Information enters from multiple sources. Rumi Rummages through it. Your Stash remembers. Your AI recalls.
Built for production
AI memory
Governed memory for working agents. Capture useful knowledge, manage its lifecycle, and bring it back into the right project.
Deterministic Control Plane
Separate reasoning from memory policy. Apply explicit rules to admission, conflict handling, and recall. Keep governance in the control plane.
Hybrid Semantic Search
Find stored knowledge by meaning and keywords. Hybrid retrieval brings relevant memories back with the context needed to use them.
Claim Lifecycle Governance
Candidate. Confirmed. Stale. Superseded. Conflicted. Archived. Track claims through their lifecycle with provenance, citations, and human review.
MCP-Native Integration
Connect compatible AI agents through MCP. Use REST for application workflows. Save and retrieve memory through the interfaces your systems use.
Local-First by Default
Run memory processing on your infrastructure. Use configured local models for embeddings and generation. Your environment. Your deployment choices.
Secret Redaction & Credential Vault
Detect supported secrets at write time. Route detected values to an encrypted credential vault and keep references in memory. If the vault is unavailable, redact detected values and preserve the remaining content.
Persistent Ingestion
Bring agent outputs and supported imports into persistent memory. Enrichment prepares stored content for later recall.
Namespaces & Tags
Organize memories with project scope, categories, tags, source details, and agent metadata. Search within the context you intend.
Short & Long Term Memory
Keep durable knowledge in the Stash and temporary working state in namespaced sessions. Session expiry is configurable.
Session Continuity
New session. Same project. Persistent memory and namespaced session state let connected agents pick up saved context after a restart. Session expiry stays configurable.
Project-Scoped Memory
Separate projects. Scoped recall. Organize memory by user and project, with machine context where configured. Retrieve from the intended scope.
Mission Control
Your Stash, in view. Browse and edit memories, watch the Live Activity feed as items are saved, updated, merged, or archived, and explore connections through the memory graph.
Operational Visibility
A watchdog checks the full stack every five minutes and emails you the moment something breaks — and again when it recovers. A daily status report arrives every morning. You don’t watch it. It tells you.
Manage what stays in the Stash.
Create, read, update, and delete memories through MCP or REST. Content hashing supports duplicate detection and integrity checks. Deleted memories move to Trash. Export memories and sessions as JSON. Archived memories stay re-importable, and every memory in your Stash carries its search vector — if it’s saved, it’s findable.
Discuss Your WorkflowPlug into your
existing stack
Connect agents through MCP and applications through REST. Keep memory available to the workflows that need it.
MCP Protocol
Use memory tools from compatible MCP clients. Configure the connection and project scope for each agent.
REST API
Create, retrieve, update, and delete memories through HTTP interfaces that require authenticated access on every call. Build memory into your application workflows without exposing an open endpoint.
Memory Import
Bring supported exports and content into the Stash. Use Mission Control to manage imports and inspect stored information.
Custom Agent Workflows
Connect your agent framework through the supported interfaces. Discuss the integration requirements for your environment.
How the memory
workflow works
1Ingestion & Enrichment
Information enters through connected agents, MCP, REST, or supported imports. Rummage organizes the incoming content, enriches its metadata, and prepares it for storage and retrieval.
2Governance & Review
The control plane applies admission policies and claim lifecycle rules. Provenance stays attached. Conflicting information moves through resolution and review workflows.
3Stash Persistence
Store durable knowledge in the Stash. Keep project context scoped and temporary session state on its configured expiry schedule. Detected credentials are handled separately through the encrypted vault or fallback redaction.
4Recall & Reuse
Retrieve relevant knowledge with source context. Bring saved decisions, constraints, and lessons back into a connected agent’s workflow.